{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:09:52Z","timestamp":1730210992349,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T00:00:00Z","timestamp":1645574400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T00:00:00Z","timestamp":1645574400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,2,23]]},"DOI":"10.1109\/csicc55295.2022.9780494","type":"proceedings-article","created":{"date-parts":[[2022,5,27]],"date-time":"2022-05-27T21:49:58Z","timestamp":1653688198000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Attention-based Persian Language Modeling"],"prefix":"10.1109","author":[{"given":"Arman","family":"Yekkehkhani","sequence":"first","affiliation":[{"name":"Allameh Tabataba’i University,Computer Science Dept,Tehran,Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammadjalal","family":"Pouromid","sequence":"additional","affiliation":[{"name":"Allameh Tabataba’i University,Computer Science Dept,Tehran,Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad","family":"Bahrani","sequence":"additional","affiliation":[{"name":"Allameh Tabataba’i University,Computer Science Dept,Tehran,Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"arXiv preprint arXiv 2005 14354"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref12","article-title":"Xlnet: Generalized autoregressive pretraining for language un-derstanding","author":"yang","year":"2019","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISTEL.2012.6483172"},{"key":"ref14","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref15","article-title":"A bit of progress in language modeling, extended version","author":"joshua t","year":"2001","journal-title":"Technical Report MSR-TR-2001-72"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5709"},{"key":"ref19","article-title":"Beheshti-NER: Persian named entity recognition Using BERT","author":"taher","year":"2020","journal-title":"arXiv preprint arXiv 2003 07516"},{"key":"ref4","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"ArXiv abs\/1310 4546"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref5","article-title":"Manning. Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"EMNLP"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"radford","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref2","first-page":"207","article-title":"Persian language modeling using recurrent neural networks","author":"habib","year":"2018","journal-title":"2018 9th International Symposium on Telecommunications (IST)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-720"},{"key":"ref9","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref20","article-title":"Bert has a mouth, and it must speak: Bert as a markov random field language model","author":"wang","year":"2019","journal-title":"arXiv preprint arXiv 1902 06673"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CSICC52343.2021.9420569"}],"event":{"name":"2022 27th International Computer Conference, Computer Society of Iran (CSICC)","start":{"date-parts":[[2022,2,23]]},"location":"Tehran, Iran, Islamic Republic of","end":{"date-parts":[[2022,2,24]]}},"container-title":["2022 27th International Computer Conference, Computer Society of Iran (CSICC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9780464\/9780394\/09780494.pdf?arnumber=9780494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T20:03:44Z","timestamp":1657569824000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9780494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/csicc55295.2022.9780494","relation":{},"subject":[],"published":{"date-parts":[[2022,2,23]]}}}